{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:24:27Z","timestamp":1756992267095,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981794","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"5171-5178","source":"Crossref","is-referenced-by-count":9,"title":["Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking"],"prefix":"10.1109","author":[{"given":"Yi","family":"Dong","sequence":"first","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"New foresight review on robotics and autonomous systems","author":"Lane","year":"2016","journal-title":"Lloyds Register Foundation, London, U.K., Tech. Rep. No. 2016.1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2004.2"},{"key":"ref3","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2021.107229"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2352\/issn.2470-1173.2017.19.avm-023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341714"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2861945"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2019.2898964"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref12","article-title":"Shielded decision-making in mdps","author":"Jansen","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Zhang","year":"2020"},{"key":"ref14","article-title":"Towards identifying and closing gaps in assurance of autonomous road vehicles-a collection of technical notes part 1","author":"Bloomfield","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-018-00646-w"},{"issue":"42","key":"ref16","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Fern","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2912958"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018066"},{"key":"ref19","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"Berkenkamp","year":"2017","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Safe reinforcement learning for probabilistic reachability and safety specifications: A lyapunov-based approach","author":"Huh","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref22","article-title":"Emergent complexity via multi-agent competition","author":"Bansal","year":"2018","journal-title":"ICLR\u201918"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref24","first-page":"97","article-title":"Re-luplex: An efficient SMT solver for verifying deep neural networks","author":"Katz","year":"2017","journal-title":"CAV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/368"},{"volume-title":"Verifiably safe autonomy for cyber-physical systems","year":"2018","author":"Fulton","key":"ref26"},{"key":"ref27","first-page":"2499","article-title":"Verifiable reinforcement learning via policy extraction","volume-title":"Proc. of the 32nd Int. Conf. on Neural Information Processing Systems, ser. NIPS18","author":"Bastani"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314638"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2016","journal-title":"ICLR16"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57685-5_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30446-1_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SEAMS.2017.19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22110-1_47"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63390-9_31"},{"key":"ref36","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"Christiano","year":"2016","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"volume-title":"Robotis(2019) turtlebot3 - e-manual, waffle pi","year":"2021","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594470"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968126"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2009.5070513"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2015.2452931"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1201\/9781315605685"},{"issue":"3.2","key":"ref44","first-page":"5","article-title":"Ros: an open-source robot operating system","volume-title":"ICRA workshop on open source software","volume":"3","author":"Quigley"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981794.pdf?arnumber=9981794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:33:05Z","timestamp":1706758385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981794","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}